# dalle2

suddenly i don't want everyone in the world to have access to i only want those with...i don't know...what's it called...tip of my tongue...

but i don't want everyone in the world to have access to DALL-E.

:)

(illustration by DALL-E)

0 1
2022-05-06

Four DIP + CLIP ViT-B/32 outputs for "a gateway between dreams", using a new model I am training to sample CLIP image embeds given a text embed (like the DALL-E 2 prior). It considerably increases the diversity of outputs for a prompt for things like DIP+CLIP and VQGAN+CLIP!

13 121
2022-05-05

いきなり出てきたのがこれで、心を打たれた。
Dall-e-2
https://t.co/G2DL0jB2ns

0 0
2022-05-02

Them: Goots is fake, AI can't make that
Dall-E 2: GROSE

1 7
2022-05-01

Well, if you want an idea. (Superhero) wearing (superhero) suit creates a nice amalgamation between both supers. At least it worked with latent diffusion and rudall-e.

0 1
2022-04-30

ruDALL-E Aspect Ratio Text-to-Image from is now included in Visions of Chaos.
https://t.co/YJcHEjBc73
"a black and white photo of a werewolf"
"a lounge room"
"an evil clown"
"dense woodland"

5 26
2022-04-29

The reaction of artists to Dall-e-2 reminded me of this scene from watchmen.

1 5
2022-04-26

On the wait list for Dall-E 2

Anyone know a way to get access now?

It will change the approach to making images so profoundly, I can't wait to get my grubby paws on it! 🐩🐩

0 0
2022-04-23

最新AI「DALL-E2」の生成画像、本当にクオリティが高いし、幅広い画像を生成できてるから無限に見てられる

69 232
2022-04-19

How I feel waiting for a Dall-E 2 invite

0 1
2022-04-16

This is pure magic 🧙‍♀️

I am trying to improve myself on prompting. For this you have to try many times switching between keywords. Expressions are so important that I can call prompting an art in itself. Check out what DALL-e 2 has produced.

0 39
2022-04-13

DALL-E2 es un nuevo sistema abierto de Inteligencia Aritificial que permite crear imagenes a partir de descripciones, combinando sujetos, objetos, temas y estilos.
Por ejemplo:
Astronautas jugando basket con gatitos, en estilo libro de niñes.

79 371
2022-04-10

Here's what a few years of progress on text-to-image generation looks like, one prompt at a time.

"Frank Sinatra as a purple alien in surrealist style"

1) AttnGAN (2018)
2) CLIP+VQGAN (2020)
3) CLIP+Diffusion (2021)
4) DALL-E 2 (2022)

87 315
2022-04-09

Dear furry artists:

Good luck and godspeed.

Skynet I mean DALL-E is coming for you.

90 579
2022-04-09

You can't draw a good rabbit DALL-E.

0 1
2022-04-08

DALL-E illustrations of "all roads lead to the same place, peaceful girl meditating for eternity"

2 38
2022-04-08

Trying out a new avi generated by DALL-E, I like that it captures my vibe from an old pic

0 82
2022-04-08

DALL-E illustrations of "fantasy illustration of cyclical scientific discovery throughout history, hopeful and bright" and "independent scientists joining back into the tree of knowledge, cyclical nature of life, bright pastel"

1 47
2022-04-08